Method and system for pre-processing of an EEG signal for cognitive load measurement

Patent metadata

Field	Value
Publication number	US-11154229-B2
Application number	US-201615765763-A
Country	US
Kind code	B2
Filing date	Oct 4, 2016
Priority date	Oct 5, 2015
Publication date	Oct 26, 2021
Grant date	Oct 26, 2021

Abstract

A method and system is provided for pre-processing of an electroencephalography (EEG) signal for cognitive load measurement. The present application provides a method and system for pre-processing of electroencephalography signal for cognitive load measurement of a user, comprises of capturing the electroencephalography signal from the head of the user, detecting the plurality of system artifacts in the captured electroencephalography signal, detecting and removing noisy window from the captured electroencephalography signal, detecting an eye blink region and filtering out said detected eye blink region from the captured electroencephalography signal, utilizing the filtered electroencephalography signal for measuring the cognitive load of the user and subsequently computing different levels of mental workloads on the user using variation of spatial distribution of frontal scalp EEG electrodes for measured cognitive load.

First claim

We claim:

1. A method for pre-processing of an electroencephalography (EEG) signal of a user for cognitive load measurement, said method comprising processor implemented steps of:
a) capturing the electroencephalography signal of the user using an electroencephalography signal recording device ( 202 ), wherein the electroencephalography signal is generated corresponding to a stroop stimulus, wherein the electroencephalography signal is a low resolution electroencephalography signal, and wherein the electroencephalography signal recording device is a low resolution device;
b) detecting a plurality of system artifacts in the captured electroencephalography signal using an artifact detection module ( 204 );
c) removing a noisy window from said electroencephalography signal using a noisy window removal module ( 206 ), wherein the noisy window is removed by detecting the noisy window using a signal skewness measurement, wherein the signal skewness measurement of the electroencephalography signal is measured by subdividing the electroencephalography signal into non overlapping windows, and wherein a non overlapping window is detected as the noisy window if the measured signal skewness measurement is less than a predefined threshold;
d) detecting an eye blink region in said electroencephalography signal using an eye blink region detection module ( 208 ), wherein the eye blink region is detected using a clustering based method, the clustering based method comprising steps of:
sub-dividing the electroencephalography signal into overlapping windows, wherein each window of the overlapping windows has a windows size of one second;
calculating a delta band power for each window of the overlapping windows as features;
applying a standard k-means algorithm on the features;
varying number of clusters and examining value of k that gives minimum Xie-Beni index, wherein the Xie-Beni index indicates finest formation of clusters; and
extracting electroencephalography data from a cluster corresponding to maximum size conditioned to lowest delta band power and marking data corresponding to remaining clusters as eye blink regions;

e) filtering out said detected eye blink region from the electroencephalography signal using an eye blink region filtering module ( 210 ); and
f) utilizing the filtered electroencephalography signal to measure discrimination of the cognitive load as a high mental workload or a low mental workload, among selected channels of the user and subsequently calculating different levels of mental workloads on the user using variation of spatial distribution of frontal scalp EEG electrodes for measured cognitive load using cognitive load measurement module ( 212 ), wherein the cognitive load for each channel is obtained using a product of change in mean frequencies and corresponding power for both alpha and theta band, the change measured between the filtered electroencephalography signal for stroop stimulus and initial baseline data, and wherein the discrimination of the cognitive load is obtained as a standard deviation of the cognitive load among the selected channels.

2. The method of claim 1 , wherein the plurality of system artifacts includes artifacts pertaining to said electroencephalography signal recording device ( 202 ).

3. The method of claim 2 , wherein the plurality of system artifacts pertaining to said electroencephalography signal recording device ( 202 ) is selected from a group comprising of power supply interference, an impedance fluctuation, a spurious noise and an electrical noise and a combination thereof.

4. The method of claim 1 , further comprises of indicating a noise level of the noisy window of said electroencephalography signal, wherein the noise level of the noisy window is selected from a group comprising of no signal, very poor signal, poor signal, fair signal and good signal.

5. The method of claim 1 , wherein the eye blink region is filtered out from the electroencephalography signal using selective high pass filters.

6. The method of claim 1 , wherein the discrimination of cognitive load is between at least two levels of measured cognitive load of the user.

7. A system ( 200 ) for pre-processing of an electroencephalography signal of a user for cognitive load measurement, the system ( 200 ) comprising:
a) a processor;
b) a memory coupled to said processor, the processor configured to perform steps of:
capturing the electroencephalography signal of the user, wherein the electroencephalography signal is generated corresponding to a stroop stimulus, wherein the electroencephalography signal is a low resolution electroencephalography signal;
detecting a plurality of system artifacts in the captured electroencephalography signal;
removing a noisy window from said electroencephalography signal, wherein the noisy window is removed by detecting the noisy window using a signal skewness measurement, wherein the signal skewness measurement of the electroencephalography signal is measured by subdividing the electroencephalography signal into non overlapping windows, and wherein a non overlapping window is detected as the noisy window if the measured signal skewness measurement is less than a predefined threshold;
detecting an eye blink region in said electroencephalography signal, wherein the eye blink region is detected using a clustering based method, the clustering based method comprising steps of:
sub-dividing the electroencephalography signal into overlapping windows, wherein each window of the overlapping windows has a windows size of one second;
calculating a delta band power for each window of the overlapping windows as features;
varying number of clusters and examining value of k that gives minimum Xie-Beni index, wherein the Xie-Beni index indicates finest formation of clusters; and
extracting electroencephalography data from a cluster corresponding to maximum size conditioned to lowest delta band power and marking data corresponding to remaining clusters as eye blink regions;

filtering out said detected eye blink region from the electroencephalography signal for measuring the cognitive load of the user; and
utilizing the filtered electroencephalography signal to measure discrimination of the cognitive load as a high mental workload or a low mental workload, among selected channels of the user and subsequently calculating different levels of mental workloads on the user using variation of spatial distribution of frontal scalp EEG electrodes for measured cognitive load, wherein the cognitive load for each channel is obtained using a product of change in mean frequencies and corresponding power for both alpha and theta band, the change measured between the filtered electroencephalography signal for stroop stimulus and initial baseline data, and wherein the discrimination of the cognitive load is obtained as a standard deviation of the cognitive load among the selected channels.

8. The system of claim 7 , wherein the eye blink region is filtered out from the electroencephalography signal using selective high pass filters.

9. The system of claim 7 , wherein the plurality of system artifacts includes artifacts pertaining to an electroencephalography signal recording device ( 202 ).

10. The system of claim 9 , wherein the plurality of system artifacts pertaining to said electroencephalography signal recording device ( 202 ) is selected from a group comprising of power supply interference, an impedance fluctuation, a spurious noise and an electrical noise and a combination thereof.

Assignees

• Tata Consultancy Services Ltd

Inventors

• Das Rajat Kumar
• Sinha Aniruddha
• Chatterjee Debatri
• Datta Shreyasi
• Gavas Rahul Dasharath

Classifications

• A61B5/384

  Recording apparatus or displays specially adapted therefor · CPC title

• A61B5/377

  using evoked responses · CPC title

• A61B5/291

  for electroencephalography [EEG] · CPC title

• A61B5/374 Primary

  Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves · CPC title

• A61B5/316 Primary

  Modalities, i.e. specific diagnostic methods · CPC title